Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1677a7459c4c4b9d75f1e24e1fdbdfae9ff62439110e151b1d1472e6597322c1
+oid sha256:7959cae58e80bd0fb8d60d65a45f63b1f579738614b5db62741600cc49fa2268
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3547f9b59c0281c53ad382d3c5c7e9d7f787187e0c526f4664d08bfd6372dc5
+oid sha256:8c94ac4108c23214031109b0807c6e70cfc2cf7ab70e771d0b1c98216fc96d2f
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0163265306122449,
+  "epoch": 0.024489795918367346,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 27.855,
       "eval_steps_per_second": 13.928,
       "step": 10
+    },
+    {
+      "epoch": 0.017959183673469388,
+      "grad_norm": 3.9569554328918457,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 13.3281,
+      "step": 11
+    },
+    {
+      "epoch": 0.019591836734693877,
+      "grad_norm": 4.2396979331970215,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 14.9336,
+      "step": 12
+    },
+    {
+      "epoch": 0.02122448979591837,
+      "grad_norm": 3.776480197906494,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 13.7148,
+      "step": 13
+    },
+    {
+      "epoch": 0.022857142857142857,
+      "grad_norm": 3.915137767791748,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 13.293,
+      "step": 14
+    },
+    {
+      "epoch": 0.024489795918367346,
+      "grad_norm": 5.005204677581787,
+      "learning_rate": 5e-05,
+      "loss": 15.0547,
+      "step": 15
+    },
+    {
+      "epoch": 0.024489795918367346,
+      "eval_loss": 0.8632168769836426,
+      "eval_runtime": 36.7318,
+      "eval_samples_per_second": 28.096,
+      "eval_steps_per_second": 14.048,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4264026791936e+16,
+  "total_flos": 2.096811938414592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null